krackers
Joined 11 years ago
Karma
4,685
Submissions
1,801
Member since
Jul 6
Recent submissions
Comment · 1 day ago
There's also a good explanation on Fortnow's blog https://blog.computationalcomplexity.org/2026/10/the-exponen...
Comment · 1 day ago
Oh I remember this from the classic SO post, but it was just presented as a funny trick. I never realized that it solves the issue mentioned in the article and there is a legitimate use-case for post-decrement in the comparison itself.
https://stackoverflow.com/questions/1642028/what-is-the-oper...
Comment · 1 day ago
>$1 in 2008 is worth $1.56 today
That's an odd way of phrasing it, since the $1 is still worth $1, and a naive reading would make you think it's "worth more" when the buying power has actually reduced.
Wouldn't it be clearer to say $1 today only buys you 64% of what you could have bought in 2008.
Comment · 1 day ago
Well the blog _is_ called "the web scraping club", maybe that's part of the challenge?
Comment · 2 days ago
Are you thinking of this one?
https://www.anthropic.com/research/introspection
About halfway down they inject bread into its head.
Comment · 2 days ago
You don't even need SAE for residual stream based steering, you can do so much more naively by just taking the average difference in activations of prompted vs. unprompted versions, then PCA to get a "control vector" that you can use to elicit the prompted behavior
Comment · 2 days ago
The single-neuron steering stuff has been going around twitter lately, do you happen to know who was the first one to do it?
I wonder how this squares with the recent "NNs are already clean" interpretability finding, which may have also been the impetus for this kind of research. Similar to their work on CNNs, maybe residual-steering is overkill, there might be just a single neuron that "cleanly" corresponds to "evilness" that you can turn up/down?
Comment · 2 days ago
Is this why UI elements have gotten bigger and rounder?
Comment · 2 days ago
>used to use the same certificate store as the rest of the OS
It was technically curl that dropped SecureTransport but I guess because no one at Apple was willing to maintain it and it apparently is a frozen API that doesn't support newer than TLS 1.2 (!). For a while their inbuilt curl could use both but preferred LibreSSL anyway.
https://daniel.haxx.se/blog/2025/01/14/secure-transport-supp...
Comment · 2 days ago
You can do that too with spectral graph theory!
Comment · 2 days ago
The thing is Apple used to do this correctly. Back when they still shipped OpenSSL (albeit some ancient version), they had actually patched OpenSSL to do cert validation against the native keychain and only ever had Keychain as the source of truth. You can see this in https://github.com/apple-oss-distributions/OpenSSL098/blob/O...
And curl was patched to use the native TLS implementation (SecureTransport) which obviously used Keychain as well.
For some reason when they switched to LibreSSL everywhere they decided to ship their own copy? I don't know what they were thinking.
Comment · 3 days ago
Link to authors' summary: https://x.com/neurostrow/status/2114778125896933442#m
It answers one of the conceptual questions that came to mind as to why it's even a well-defined concept:
> When the Jacobian is studied in an LLM, it provides directions in the residual stream that are “verbalizable” (Gurnee et al., 2026), which is to say that it identifies how perturbations change the linguistic output of the model. However, this property holds only in the local neighborhood of the point on which the Jacobian is defined, and the J-lens is defined by averaging over prompts, tokens, and future positions in the output layer. An average Jacobian has no reason to behave like any of its elements.